Coordination cost in human–AI systems

Coordination cost in heterogeneous AI tool ecosystems. Outside-reader brief on what the program studies, why now, and what it contributes.

What AI does to human capability over time. Penwright is the lead empirical apparatus; the broader frame extends to AI as long-term cognitive partner across professions and domains.

Operational discipline (assignment registry, handoff protocol, two-phase actor handoff, shared-index commit, coordination-event log) plus research discipline (pre-registered predictions, falsifiable constructs, acknowledged researcher position, threats-to-validity register).

The full three-arm research program: Agent↔Agent, Human↔AI, and Interface (the lead arm). C1 — risk compensation in human-AI coordination — is the lead study. Theoretical lineage across cockpit HCI, CSCW, empirical SE, behavioral decision-making, and stigmergic-coordination literatures.

Five parallel cluster lenses (coordination, working alliance, trust calibration, governance, identity) synthesized 143 raw features from the AI-research corpus into a Now/Next/Later/Killed slate. Documents the convergence map (which primitives appeared in 3+ clusters) and the decision rule that filed 14 cards into the shipping wave.

Cross-references the post-2010 phenomenology-of-attention literature (Stiegler, Citton, Hayles) and phenomenology-of-skill (Dreyfus, Merleau-Ponty, Heersmink) against the 14-card synthesis slate. Surfaces what the existing measurement set covers (verification load, withdrawal disruption) and what it misses (sustained reasoning duration, situation-disclosing experience, transparency-vs-incorporation). Source for DP-88 (sustained-reasoning window) and DP-91 (phenomenology probe).

Inventory of AI surfaces across vela and meta-factory, mapped to the 14-card synthesis slate. Identifies which devplane primitives port directly to other portfolio apps (origin marker, multi-axis reviewer, sycophancy circuit-breaker) and which require app-specific adaptation. Source document for the cross-repo dispatch wave (DP-93 through DP-96).

Track A — twelve sub-papers across three tiers (foundational theory · measurement and mechanism · longitudinal empirical studies) drawing from a shared dataset generated by Penwright in production. Track B — six cross-cutting research programs the Penwright evidence may eventually seed.

Adversarial review of the DevPlane research instrument: the two-phase actor handoff, the coordination-event log schema, multi-tool sync drift across claude-code/cursor/codex, and the completion-block protocol. Names specific failure modes (fire-and-forget write drops, build-agent-skips-review shortcut, agent_started step-function pre/post DP-102, polling-bound merge detection) and a ranked fix list before the corpus carries weight.

What the research program tells a product builder thinking about coordination tooling for human-AI software development. What to build into DevPlane next, what to build into adjacent tools, what the broader product space gets wrong — traceable to architectural decisions and pre-registered predictions, with honest pre-data caveats where applicable.

Cockpit/process-control HCI · CSCW · empirical software engineering · behavioral decision-making · multi-agent systems and stigmergic coordination. With explicit confidence flags ([C] canonical, [F] field-level, [DR] open for deep-research expansion).

Index of 29 secondary literature reviews + 6 cross-LLM syntheses, organized by the twelve-branch HAI field map plus frontier zones, adjacent fields, and deep intersections. Honest gap-flagging at the bottom.

The twelve-branch HAI field map, frontier zones, adjacent fields the mainstream has under-engaged, deep intersections where genuine theoretical integration is possible, and six cross-cutting research programs. Verbatim source — load-bearing field orientation.

Formal proposal for the C1 lead study. Pre-registered hypotheses with yes-world / no-world consequences; pre-committed coding rules for failure attribution; Bayesian structural time-series analysis plan; threats-to-validity register. The proposal serves as pre-registration in spirit; formal OSF filing follows once the analysis pipeline is built and a run-in period of data is collected.